Merge tag 'kvm_mips_4.12_1' of git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/kvm-mips
From: James Hogan <james.hogan@imgtec.com>
KVM: MIPS: VZ support, Octeon III, and TLBR
Add basic support for the MIPS Virtualization Module (generally known as
MIPS VZ) in KVM. We primarily support the ImgTec P5600, P6600, I6400,
and Cavium Octeon III cores so far. Support is included for the
following VZ / guest hardware features:
- MIPS32 and MIPS64, r5 (VZ requires r5 or later) and r6
- TLBs with GuestID (IMG cores) or Root ASID Dealias (Octeon III)
- Shared physical root/guest TLB (IMG cores)
- FPU / MSA
- Cop0 timer (up to 1GHz for now due to soft timer limit)
- Segmentation control (EVA)
- Hardware page table walker (HTW) both for root and guest TLB
Also included is a proper implementation of the TLBR instruction for the
trap & emulate MIPS KVM implementation.
Preliminary MIPS architecture changes are applied directly with Ralf's
ack.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index e601c8f..753e88e 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3400,6 +3400,69 @@
__u32 pad;
};
+4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: system ioctl
+Parameters: u64 mce_cap (out)
+Returns: 0 on success, -1 on error
+
+Returns supported MCE capabilities. The u64 mce_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register. Supported
+capabilities will have the corresponding bits set.
+
+4.105 KVM_X86_SETUP_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: u64 mcg_cap (in)
+Returns: 0 on success,
+ -EFAULT if u64 mcg_cap cannot be read,
+ -EINVAL if the requested number of banks is invalid,
+ -EINVAL if requested MCE capability is not supported.
+
+Initializes MCE support for use. The u64 mcg_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register and
+specifies which capabilities should be enabled. The maximum
+supported number of error-reporting banks can be retrieved when
+checking for KVM_CAP_MCE. The supported capabilities can be
+retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
+
+4.106 KVM_X86_SET_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_x86_mce (in)
+Returns: 0 on success,
+ -EFAULT if struct kvm_x86_mce cannot be read,
+ -EINVAL if the bank number is invalid,
+ -EINVAL if VAL bit is not set in status field.
+
+Inject a machine check error (MCE) into the guest. The input
+parameter is:
+
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+
+If the MCE being reported is an uncorrected error, KVM will
+inject it as an MCE exception into the guest. If the guest
+MCG_STATUS register reports that an MCE is in progress, KVM
+causes an KVM_EXIT_SHUTDOWN vmexit.
+
+Otherwise, if the MCE is a corrected error, KVM will just
+store it in the corresponding bank (provided this bank is
+not holding a previously reported uncorrected error).
+
5. The kvm_run structure
------------------------
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b..c4eda79 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
};
void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 73ea24d..047b17a 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm)
{
struct kvm_pic *vpic = kvm->arch.vpic;
+ if (!vpic)
+ return;
+
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 6e219e5..289270a 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ if (!ioapic)
+ return;
+
cancel_delayed_work_sync(&ioapic->eoi_inject);
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
kvm->arch.vioapic = NULL;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 37942e4..60168cd 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
}
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_head *head;
+
+ head = &kvm->arch.track_notifier_head;
+ cleanup_srcu_struct(&head->track_srcu);
+}
+
void kvm_page_track_init(struct kvm *kvm)
{
struct kvm_page_track_notifier_head *head;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d1efe2c..5fba706 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1379,6 +1379,9 @@ static void avic_vm_destroy(struct kvm *kvm)
unsigned long flags;
struct kvm_arch *vm_data = &kvm->arch;
+ if (!avic)
+ return;
+
avic_free_vm_id(vm_data->avic_vm_id);
if (vm_data->avic_logical_id_table_page)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 98e82ee..2ee00db 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1239,6 +1239,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}
+static inline bool cpu_has_vmx_invvpid(void)
+{
+ return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -2753,7 +2758,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
- SECONDARY_EXEC_ENABLE_VPID |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING |
@@ -2781,10 +2785,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
* though it is treated as global context. The alternative is
* not failing the single-context invvpid, and it is worse.
*/
- if (enable_vpid)
+ if (enable_vpid) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_VPID;
vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
VMX_VPID_EXTENT_SUPPORTED_MASK;
- else
+ } else
vmx->nested.nested_vmx_vpid_caps = 0;
if (enable_unrestricted_guest)
@@ -4024,6 +4030,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
}
+static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
+{
+ if (enable_ept)
+ vmx_flush_tlb(vcpu);
+}
+
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -6517,8 +6529,10 @@ static __init int hardware_setup(void)
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
- if (!cpu_has_vmx_vpid())
+ if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+ !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
enable_vpid = 0;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs)
@@ -8501,7 +8515,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+ vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+ exit_reason);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
@@ -8547,6 +8562,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
} else {
sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ vmx_flush_tlb_ept_only(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
@@ -8572,8 +8588,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
*/
if (!is_guest_mode(vcpu) ||
!nested_cpu_has2(get_vmcs12(&vmx->vcpu),
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
+ vmx_flush_tlb_ept_only(vcpu);
+ }
}
static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
@@ -9974,7 +9992,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control;
- bool nested_ept_enabled = false;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10121,8 +10138,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs12->guest_intr_status);
}
- nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
-
/*
* Write an illegal value to APIC_ACCESS_ADDR. Later,
* nested_get_vmcs12_pages will either fix it up or
@@ -10255,6 +10270,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
+ } else if (nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ vmx_flush_tlb_ept_only(vcpu);
}
/*
@@ -10282,12 +10300,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmx_set_efer(vcpu, vcpu->arch.efer);
/* Shadow page tables on either EPT or shadow page tables. */
- if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
entry_failure_code))
return 1;
- kvm_mmu_reset_context(vcpu);
-
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
@@ -11056,6 +11072,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
vmx_set_virtual_x2apic_mode(vcpu,
vcpu->arch.apic_base & X2APIC_ENABLE);
+ } else if (!nested_cpu_has_ept(vmcs12) &&
+ nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ vmx_flush_tlb_ept_only(vcpu);
}
/* This is needed for same reason as it was needed in prepare_vmcs02 */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1faf620..ccbd45e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
if (kvm_x86_ops->vm_destroy)
kvm_x86_ops->vm_destroy(kvm);
kvm_iommu_unmap_guest(kvm);
- kfree(kvm->arch.vpic);
- kfree(kvm->arch.vioapic);
+ kvm_pic_destroy(kvm);
+ kvm_ioapic_destroy(kvm);
kvm_free_vcpus(kvm);
kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kvm_mmu_uninit_vm(kvm);
+ kvm_page_track_cleanup(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
{
struct x86_exception fault;
- trace_kvm_async_pf_ready(work->arch.token, work->gva);
if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+ trace_kvm_async_pf_ready(work->arch.token, work->gva);
if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c
index 09b4df7..bb86569 100644
--- a/drivers/ptp/ptp_kvm.c
+++ b/drivers/ptp/ptp_kvm.c
@@ -193,10 +193,7 @@ static int __init ptp_kvm_init(void)
kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL);
- if (IS_ERR(kvm_ptp_clock.ptp_clock))
- return PTR_ERR(kvm_ptp_clock.ptp_clock);
-
- return 0;
+ return PTR_ERR_OR_ZERO(kvm_ptp_clock.ptp_clock);
}
module_init(ptp_kvm_init);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2c14ad9..d025074 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -162,8 +162,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, void *val);
int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, struct kvm_io_device *dev);
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
- struct kvm_io_device *dev);
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ struct kvm_io_device *dev);
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
gpa_t addr);
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 581278c..8f74ed8 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -30,8 +30,8 @@
import resource
import struct
import re
+import subprocess
from collections import defaultdict
-from time import sleep
VMX_EXIT_REASONS = {
'EXCEPTION_NMI': 0,
@@ -225,6 +225,7 @@
'RESET': 0x00002403,
}
+
class Arch(object):
"""Encapsulates global architecture specific data.
@@ -255,12 +256,14 @@
return ArchX86(SVM_EXIT_REASONS)
return
+
class ArchX86(Arch):
def __init__(self, exit_reasons):
self.sc_perf_evt_open = 298
self.ioctl_numbers = IOCTL_NUMBERS
self.exit_reasons = exit_reasons
+
class ArchPPC(Arch):
def __init__(self):
self.sc_perf_evt_open = 319
@@ -275,12 +278,14 @@
self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
self.exit_reasons = {}
+
class ArchA64(Arch):
def __init__(self):
self.sc_perf_evt_open = 241
self.ioctl_numbers = IOCTL_NUMBERS
self.exit_reasons = AARCH64_EXIT_REASONS
+
class ArchS390(Arch):
def __init__(self):
self.sc_perf_evt_open = 331
@@ -316,6 +321,61 @@
return integers
+def get_pid_from_gname(gname):
+ """Fuzzy function to convert guest name to QEMU process pid.
+
+ Returns a list of potential pids, can be empty if no match found.
+ Throws an exception on processing errors.
+
+ """
+ pids = []
+ try:
+ child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'],
+ stdout=subprocess.PIPE)
+ except:
+ raise Exception
+ for line in child.stdout:
+ line = line.lstrip().split(' ', 1)
+ # perform a sanity check before calling the more expensive
+ # function to possibly extract the guest name
+ if ' -name ' in line[1] and gname == get_gname_from_pid(line[0]):
+ pids.append(int(line[0]))
+ child.stdout.close()
+
+ return pids
+
+
+def get_gname_from_pid(pid):
+ """Returns the guest name for a QEMU process pid.
+
+ Extracts the guest name from the QEMU comma line by processing the '-name'
+ option. Will also handle names specified out of sequence.
+
+ """
+ name = ''
+ try:
+ line = open('/proc/{}/cmdline'.format(pid), 'rb').read().split('\0')
+ parms = line[line.index('-name') + 1].split(',')
+ while '' in parms:
+ # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results in
+ # ['foo', '', 'bar'], which we revert here
+ idx = parms.index('')
+ parms[idx - 1] += ',' + parms[idx + 1]
+ del parms[idx:idx+2]
+ # the '-name' switch allows for two ways to specify the guest name,
+ # where the plain name overrides the name specified via 'guest='
+ for arg in parms:
+ if '=' not in arg:
+ name = arg
+ break
+ if arg[:6] == 'guest=':
+ name = arg[6:]
+ except (ValueError, IOError, IndexError):
+ pass
+
+ return name
+
+
def get_online_cpus():
"""Returns a list of cpu id integers."""
with open('/sys/devices/system/cpu/online') as cpu_list:
@@ -342,6 +402,7 @@
libc = ctypes.CDLL('libc.so.6', use_errno=True)
syscall = libc.syscall
+
class perf_event_attr(ctypes.Structure):
"""Struct that holds the necessary data to set up a trace event.
@@ -370,6 +431,7 @@
self.size = ctypes.sizeof(self)
self.read_format = PERF_FORMAT_GROUP
+
def perf_event_open(attr, pid, cpu, group_fd, flags):
"""Wrapper for the sys_perf_evt_open() syscall.
@@ -395,6 +457,7 @@
PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing'
PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm'
+
class Group(object):
"""Represents a perf event group."""
@@ -427,6 +490,7 @@
struct.unpack(read_format,
os.read(self.events[0].fd, length))))
+
class Event(object):
"""Represents a performance event and manages its life cycle."""
def __init__(self, name, group, trace_cpu, trace_pid, trace_point,
@@ -510,6 +574,7 @@
"""Resets the count of the trace event in the kernel."""
fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0)
+
class TracepointProvider(object):
"""Data provider for the stats class.
@@ -551,6 +616,7 @@
def setup_traces(self):
"""Creates all event and group objects needed to be able to retrieve
data."""
+ fields = self.get_available_fields()
if self._pid > 0:
# Fetch list of all threads of the monitored pid, as qemu
# starts a thread for each vcpu.
@@ -561,7 +627,7 @@
# The constant is needed as a buffer for python libs, std
# streams and other files that the script opens.
- newlim = len(groupids) * len(self._fields) + 50
+ newlim = len(groupids) * len(fields) + 50
try:
softlim_, hardlim = resource.getrlimit(resource.RLIMIT_NOFILE)
@@ -577,7 +643,7 @@
for groupid in groupids:
group = Group()
- for name in self._fields:
+ for name in fields:
tracepoint = name
tracefilter = None
match = re.match(r'(.*)\((.*)\)', name)
@@ -650,13 +716,23 @@
ret[name] += val
return ret
+ def reset(self):
+ """Reset all field counters"""
+ for group in self.group_leaders:
+ for event in group.events:
+ event.reset()
+
+
class DebugfsProvider(object):
"""Provides data from the files that KVM creates in the kvm debugfs
folder."""
def __init__(self):
self._fields = self.get_available_fields()
+ self._baseline = {}
self._pid = 0
self.do_read = True
+ self.paths = []
+ self.reset()
def get_available_fields(self):
""""Returns a list of available fields.
@@ -673,6 +749,7 @@
@fields.setter
def fields(self, fields):
self._fields = fields
+ self.reset()
@property
def pid(self):
@@ -690,10 +767,11 @@
self.paths = filter(lambda x: "{}-".format(pid) in x, vms)
else:
- self.paths = ['']
+ self.paths = []
self.do_read = True
+ self.reset()
- def read(self):
+ def read(self, reset=0):
"""Returns a dict with format:'file name / field -> current value'."""
results = {}
@@ -701,10 +779,22 @@
if not self.do_read:
return results
- for path in self.paths:
+ paths = self.paths
+ if self._pid == 0:
+ paths = []
+ for entry in os.walk(PATH_DEBUGFS_KVM):
+ for dir in entry[1]:
+ paths.append(dir)
+ for path in paths:
for field in self._fields:
- results[field] = results.get(field, 0) \
- + self.read_field(field, path)
+ value = self.read_field(field, path)
+ key = path + field
+ if reset:
+ self._baseline[key] = value
+ if self._baseline.get(key, -1) == -1:
+ self._baseline[key] = value
+ results[field] = (results.get(field, 0) + value -
+ self._baseline.get(key, 0))
return results
@@ -718,6 +808,12 @@
except IOError:
return 0
+ def reset(self):
+ """Reset field counters"""
+ self._baseline = {}
+ self.read(1)
+
+
class Stats(object):
"""Manages the data providers and the data they provide.
@@ -753,14 +849,20 @@
for provider in self.providers:
provider.pid = self._pid_filter
+ def reset(self):
+ self.values = {}
+ for provider in self.providers:
+ provider.reset()
+
@property
def fields_filter(self):
return self._fields_filter
@fields_filter.setter
def fields_filter(self, fields_filter):
- self._fields_filter = fields_filter
- self.update_provider_filters()
+ if fields_filter != self._fields_filter:
+ self._fields_filter = fields_filter
+ self.update_provider_filters()
@property
def pid_filter(self):
@@ -768,9 +870,10 @@
@pid_filter.setter
def pid_filter(self, pid):
- self._pid_filter = pid
- self.values = {}
- self.update_provider_pid()
+ if pid != self._pid_filter:
+ self._pid_filter = pid
+ self.values = {}
+ self.update_provider_pid()
def get(self):
"""Returns a dict with field -> (value, delta to last value) of all
@@ -778,23 +881,26 @@
for provider in self.providers:
new = provider.read()
for key in provider.fields:
- oldval = self.values.get(key, (0, 0))
+ oldval = self.values.get(key, (0, 0))[0]
newval = new.get(key, 0)
- newdelta = None
- if oldval is not None:
- newdelta = newval - oldval[0]
+ newdelta = newval - oldval
self.values[key] = (newval, newdelta)
return self.values
LABEL_WIDTH = 40
NUMBER_WIDTH = 10
+DELAY_INITIAL = 0.25
+DELAY_REGULAR = 3.0
+MAX_GUEST_NAME_LEN = 48
+MAX_REGEX_LEN = 44
+DEFAULT_REGEX = r'^[^\(]*$'
+
class Tui(object):
"""Instruments curses to draw a nice text ui."""
def __init__(self, stats):
self.stats = stats
self.screen = None
- self.drilldown = False
self.update_drilldown()
def __enter__(self):
@@ -809,7 +915,14 @@
# return from C start_color() is ignorable.
try:
curses.start_color()
- except:
+ except curses.error:
+ pass
+
+ # Hide cursor in extra statement as some monochrome terminals
+ # might support hiding but not colors.
+ try:
+ curses.curs_set(0)
+ except curses.error:
pass
curses.use_default_colors()
@@ -827,36 +940,60 @@
def update_drilldown(self):
"""Sets or removes a filter that only allows fields without braces."""
if not self.stats.fields_filter:
- self.stats.fields_filter = r'^[^\(]*$'
+ self.stats.fields_filter = DEFAULT_REGEX
- elif self.stats.fields_filter == r'^[^\(]*$':
+ elif self.stats.fields_filter == DEFAULT_REGEX:
self.stats.fields_filter = None
def update_pid(self, pid):
"""Propagates pid selection to stats object."""
self.stats.pid_filter = pid
- def refresh(self, sleeptime):
- """Refreshes on-screen data."""
+ def refresh_header(self, pid=None):
+ """Refreshes the header."""
+ if pid is None:
+ pid = self.stats.pid_filter
self.screen.erase()
- if self.stats.pid_filter > 0:
- self.screen.addstr(0, 0, 'kvm statistics - pid {0}'
- .format(self.stats.pid_filter),
- curses.A_BOLD)
+ gname = get_gname_from_pid(pid)
+ if gname:
+ gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...'
+ if len(gname) > MAX_GUEST_NAME_LEN
+ else gname))
+ if pid > 0:
+ self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}'
+ .format(pid, gname), curses.A_BOLD)
else:
self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD)
+ if self.stats.fields_filter and self.stats.fields_filter \
+ != DEFAULT_REGEX:
+ regex = self.stats.fields_filter
+ if len(regex) > MAX_REGEX_LEN:
+ regex = regex[:MAX_REGEX_LEN] + '...'
+ self.screen.addstr(1, 17, 'regex filter: {0}'.format(regex))
self.screen.addstr(2, 1, 'Event')
self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH -
len('Total'), 'Total')
- self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 8 -
+ self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 -
+ len('%Total'), '%Total')
+ self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 + 8 -
len('Current'), 'Current')
+ self.screen.addstr(4, 1, 'Collecting data...')
+ self.screen.refresh()
+
+ def refresh_body(self, sleeptime):
row = 3
+ self.screen.move(row, 0)
+ self.screen.clrtobot()
stats = self.stats.get()
+
def sortkey(x):
if stats[x][1]:
return (-stats[x][1], -stats[x][0])
else:
return (0, -stats[x][0])
+ total = 0.
+ for val in stats.values():
+ total += val[0]
for key in sorted(stats.keys(), key=sortkey):
if row >= self.screen.getmaxyx()[0]:
@@ -869,6 +1006,8 @@
col += LABEL_WIDTH
self.screen.addstr(row, col, '%10d' % (values[0],))
col += NUMBER_WIDTH
+ self.screen.addstr(row, col, '%7.1f' % (values[0] * 100 / total,))
+ col += 7
if values[1] is not None:
self.screen.addstr(row, col, '%8d' % (values[1] / sleeptime,))
row += 1
@@ -893,20 +1032,24 @@
regex = self.screen.getstr()
curses.noecho()
if len(regex) == 0:
+ self.stats.fields_filter = DEFAULT_REGEX
+ self.refresh_header()
return
try:
re.compile(regex)
self.stats.fields_filter = regex
+ self.refresh_header()
return
except re.error:
continue
- def show_vm_selection(self):
+ def show_vm_selection_by_pid(self):
"""Draws PID selection mask.
Asks for a pid until a valid pid or 0 has been entered.
"""
+ msg = ''
while True:
self.screen.erase()
self.screen.addstr(0, 0,
@@ -915,6 +1058,7 @@
self.screen.addstr(1, 0,
'This might limit the shown data to the trace '
'statistics.')
+ self.screen.addstr(5, 0, msg)
curses.echo()
self.screen.addstr(3, 0, "Pid [0 or pid]: ")
@@ -922,60 +1066,128 @@
curses.noecho()
try:
- pid = int(pid)
-
- if pid == 0:
- self.update_pid(pid)
- break
- else:
- if not os.path.isdir(os.path.join('/proc/', str(pid))):
+ if len(pid) > 0:
+ pid = int(pid)
+ if pid != 0 and not os.path.isdir(os.path.join('/proc/',
+ str(pid))):
+ msg = '"' + str(pid) + '": Not a running process'
continue
- else:
- self.update_pid(pid)
- break
+ else:
+ pid = 0
+ self.refresh_header(pid)
+ self.update_pid(pid)
+ break
except ValueError:
+ msg = '"' + str(pid) + '": Not a valid pid'
continue
+ def show_vm_selection_by_guest_name(self):
+ """Draws guest selection mask.
+
+ Asks for a guest name until a valid guest name or '' is entered.
+
+ """
+ msg = ''
+ while True:
+ self.screen.erase()
+ self.screen.addstr(0, 0,
+ 'Show statistics for specific guest.',
+ curses.A_BOLD)
+ self.screen.addstr(1, 0,
+ 'This might limit the shown data to the trace '
+ 'statistics.')
+ self.screen.addstr(5, 0, msg)
+ curses.echo()
+ self.screen.addstr(3, 0, "Guest [ENTER or guest]: ")
+ gname = self.screen.getstr()
+ curses.noecho()
+
+ if not gname:
+ self.refresh_header(0)
+ self.update_pid(0)
+ break
+ else:
+ pids = []
+ try:
+ pids = get_pid_from_gname(gname)
+ except:
+ msg = '"' + gname + '": Internal error while searching, ' \
+ 'use pid filter instead'
+ continue
+ if len(pids) == 0:
+ msg = '"' + gname + '": Not an active guest'
+ continue
+ if len(pids) > 1:
+ msg = '"' + gname + '": Multiple matches found, use pid ' \
+ 'filter instead'
+ continue
+ self.refresh_header(pids[0])
+ self.update_pid(pids[0])
+ break
+
def show_stats(self):
"""Refreshes the screen and processes user input."""
- sleeptime = 0.25
+ sleeptime = DELAY_INITIAL
+ self.refresh_header()
while True:
- self.refresh(sleeptime)
+ self.refresh_body(sleeptime)
curses.halfdelay(int(sleeptime * 10))
- sleeptime = 3
+ sleeptime = DELAY_REGULAR
try:
char = self.screen.getkey()
if char == 'x':
- self.drilldown = not self.drilldown
+ self.refresh_header()
self.update_drilldown()
+ sleeptime = DELAY_INITIAL
if char == 'q':
break
+ if char == 'c':
+ self.stats.fields_filter = DEFAULT_REGEX
+ self.refresh_header(0)
+ self.update_pid(0)
+ sleeptime = DELAY_INITIAL
if char == 'f':
self.show_filter_selection()
+ sleeptime = DELAY_INITIAL
+ if char == 'g':
+ self.show_vm_selection_by_guest_name()
+ sleeptime = DELAY_INITIAL
if char == 'p':
- self.show_vm_selection()
+ self.show_vm_selection_by_pid()
+ sleeptime = DELAY_INITIAL
+ if char == 'r':
+ self.refresh_header()
+ self.stats.reset()
+ sleeptime = DELAY_INITIAL
except KeyboardInterrupt:
break
except curses.error:
continue
+
def batch(stats):
"""Prints statistics in a key, value format."""
- s = stats.get()
- time.sleep(1)
- s = stats.get()
- for key in sorted(s.keys()):
- values = s[key]
- print '%-42s%10d%10d' % (key, values[0], values[1])
+ try:
+ s = stats.get()
+ time.sleep(1)
+ s = stats.get()
+ for key in sorted(s.keys()):
+ values = s[key]
+ print '%-42s%10d%10d' % (key, values[0], values[1])
+ except KeyboardInterrupt:
+ pass
+
def log(stats):
"""Prints statistics as reiterating key block, multiple value blocks."""
keys = sorted(stats.get().iterkeys())
+
def banner():
for k in keys:
print '%s' % k,
print
+
def statline():
s = stats.get()
for k in keys:
@@ -984,11 +1196,15 @@
line = 0
banner_repeat = 20
while True:
- time.sleep(1)
- if line % banner_repeat == 0:
- banner()
- statline()
- line += 1
+ try:
+ time.sleep(1)
+ if line % banner_repeat == 0:
+ banner()
+ statline()
+ line += 1
+ except KeyboardInterrupt:
+ break
+
def get_options():
"""Returns processed program arguments."""
@@ -1009,6 +1225,16 @@
CAP_SYS_ADMIN and perf events are used.
- CAP_SYS_RESOURCE if the hard limit is not high enough to allow
the large number of files that are possibly opened.
+
+Interactive Commands:
+ c clear filter
+ f filter by regular expression
+ g filter by guest name
+ p filter by PID
+ q quit
+ x toggle reporting of stats for individual child trace events
+ r reset stats
+Press any other key to refresh statistics immediately.
"""
class PlainHelpFormatter(optparse.IndentedHelpFormatter):
@@ -1018,6 +1244,22 @@
else:
return ""
+ def cb_guest_to_pid(option, opt, val, parser):
+ try:
+ pids = get_pid_from_gname(val)
+ except:
+ raise optparse.OptionValueError('Error while searching for guest '
+ '"{}", use "-p" to specify a pid '
+ 'instead'.format(val))
+ if len(pids) == 0:
+ raise optparse.OptionValueError('No guest by the name "{}" '
+ 'found'.format(val))
+ if len(pids) > 1:
+ raise optparse.OptionValueError('Multiple processes found (pids: '
+ '{}) - use "-p" to specify a pid '
+ 'instead'.format(" ".join(pids)))
+ parser.values.pid = pids[0]
+
optparser = optparse.OptionParser(description=description_text,
formatter=PlainHelpFormatter())
optparser.add_option('-1', '--once', '--batch',
@@ -1051,15 +1293,24 @@
help='fields to display (regex)',
)
optparser.add_option('-p', '--pid',
- action='store',
- default=0,
- type=int,
- dest='pid',
- help='restrict statistics to pid',
- )
+ action='store',
+ default=0,
+ type='int',
+ dest='pid',
+ help='restrict statistics to pid',
+ )
+ optparser.add_option('-g', '--guest',
+ action='callback',
+ type='string',
+ dest='pid',
+ metavar='GUEST',
+ help='restrict statistics to guest by name',
+ callback=cb_guest_to_pid,
+ )
(options, _) = optparser.parse_args(sys.argv)
return options
+
def get_providers(options):
"""Returns a list of data providers depending on the passed options."""
providers = []
@@ -1073,6 +1324,7 @@
return providers
+
def check_access(options):
"""Exits if the current user can't access all needed directories."""
if not os.path.exists('/sys/kernel/debug'):
@@ -1086,8 +1338,8 @@
"Also ensure, that the kvm modules are loaded.\n")
sys.exit(1)
- if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints
- or not options.debugfs):
+ if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or
+ not options.debugfs):
sys.stderr.write("Please enable CONFIG_TRACING in your kernel "
"when using the option -t (default).\n"
"If it is enabled, make {0} readable by the "
@@ -1098,10 +1350,11 @@
sys.stderr.write("Falling back to debugfs statistics!\n")
options.debugfs = True
- sleep(5)
+ time.sleep(5)
return options
+
def main():
options = get_options()
options = check_access(options)
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
index b92a153..109431b 100644
--- a/tools/kvm/kvm_stat/kvm_stat.txt
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -18,11 +18,33 @@
This tool is useful for observing guest behavior from the host perspective.
Often conclusions about performance or buggy behavior can be drawn from the
output.
+While running in regular mode, use any of the keys listed in section
+'Interactive Commands' below.
+Use batch and logging modes for scripting purposes.
The set of KVM kernel module trace events may be specific to the kernel version
or architecture. It is best to check the KVM kernel module source code for the
meaning of events.
+INTERACTIVE COMMANDS
+--------------------
+[horizontal]
+*c*:: clear filter
+
+*f*:: filter by regular expression
+
+*g*:: filter by guest name
+
+*p*:: filter by PID
+
+*q*:: quit
+
+*r*:: reset stats
+
+*x*:: toggle reporting of stats for child trace events
+
+Press any other key to refresh statistics immediately.
+
OPTIONS
-------
-1::
@@ -46,6 +68,10 @@
--pid=<pid>::
limit statistics to one virtual machine (pid)
+-g<guest>::
+--guest=<guest_name>::
+ limit statistics to one virtual machine (guest name)
+
-f<fields>::
--fields=<fields>::
fields to display (regex)
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index a29786d..4d28a9d 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -870,7 +870,8 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
continue;
kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
- kvm->buses[bus_idx]->ioeventfd_count--;
+ if (kvm->buses[bus_idx])
+ kvm->buses[bus_idx]->ioeventfd_count--;
ioeventfd_release(p);
ret = 0;
break;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a17d787..88257b3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -727,8 +727,11 @@ static void kvm_destroy_vm(struct kvm *kvm)
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
kvm_free_irq_routing(kvm);
- for (i = 0; i < KVM_NR_BUSES; i++)
- kvm_io_bus_destroy(kvm->buses[i]);
+ for (i = 0; i < KVM_NR_BUSES; i++) {
+ if (kvm->buses[i])
+ kvm_io_bus_destroy(kvm->buses[i]);
+ kvm->buses[i] = NULL;
+ }
kvm_coalesced_mmio_free(kvm);
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
@@ -1062,7 +1065,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
* changes) is disallowed above, so any other attribute changes getting
* here can be skipped.
*/
- if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+ if (as_id == 0 && (change == KVM_MR_CREATE || change == KVM_MR_MOVE)) {
r = kvm_iommu_map_pages(kvm, &new);
return r;
}
@@ -3474,6 +3477,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
r = __kvm_io_bus_write(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
@@ -3491,6 +3496,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
/* First try the device referenced by cookie. */
if ((cookie >= 0) && (cookie < bus->dev_count) &&
@@ -3541,6 +3548,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
r = __kvm_io_bus_read(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
@@ -3553,6 +3562,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
struct kvm_io_bus *new_bus, *bus;
bus = kvm->buses[bus_idx];
+ if (!bus)
+ return -ENOMEM;
+
/* exclude ioeventfd which is limited by maximum fd */
if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
return -ENOSPC;
@@ -3572,37 +3584,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
}
/* Caller must hold slots_lock. */
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
- struct kvm_io_device *dev)
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ struct kvm_io_device *dev)
{
- int i, r;
+ int i;
struct kvm_io_bus *new_bus, *bus;
bus = kvm->buses[bus_idx];
- r = -ENOENT;
+ if (!bus)
+ return;
+
for (i = 0; i < bus->dev_count; i++)
if (bus->range[i].dev == dev) {
- r = 0;
break;
}
- if (r)
- return r;
+ if (i == bus->dev_count)
+ return;
new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
sizeof(struct kvm_io_range)), GFP_KERNEL);
- if (!new_bus)
- return -ENOMEM;
+ if (!new_bus) {
+ pr_err("kvm: failed to shrink bus, removing it completely\n");
+ goto broken;
+ }
memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
new_bus->dev_count--;
memcpy(new_bus->range + i, bus->range + i + 1,
(new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+broken:
rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
synchronize_srcu_expedited(&kvm->srcu);
kfree(bus);
- return r;
+ return;
}
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
@@ -3615,6 +3631,8 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
srcu_idx = srcu_read_lock(&kvm->srcu);
bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+ if (!bus)
+ goto out_unlock;
dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
if (dev_idx < 0)